Amazon SageMaker Inference Router Runtime 2026-01-01
- Client: Aws\SageMakerInferenceRouterRuntime\SageMakerInferenceRouterRuntimeClient
- Service ID: sagemaker-inference-router-runtime
- Version: 2026-01-01
This page describes the parameters and results for the operations of the Amazon SageMaker Inference Router Runtime (2026-01-01), and shows how to use the Aws\SageMakerInferenceRouterRuntime\SageMakerInferenceRouterRuntimeClient object to call the described operations. This documentation is specific to the 2026-01-01 API version of the service.
Operation Summary
Each of the following operations can be created from a client using
$client->getCommand('CommandName'), where "CommandName" is the
name of one of the following operations. Note: a command is a value that
encapsulates an operation and the parameters used to create an HTTP request.
You can also create and send a command immediately using the magic methods
available on a client object: $client->commandName(/* parameters */).
You can send the command asynchronously (returning a promise) by appending the
word "Async" to the operation name: $client->commandNameAsync(/* parameters */).
- InvokeInferenceRouter ( array $params = [] )
- Sends a real-time inference request to an inference router.
- InvokeInferenceRouterAsync ( array $params = [] )
- Submits an asynchronous inference request to an inference router.
Operations
InvokeInferenceRouter
$result = $client->invokeInferenceRouter([/* ... */]); $promise = $client->invokeInferenceRouterAsync([/* ... */]);
Sends a real-time inference request to an inference router. In the request, you name the routing target, and the router sends the request to one of the routing target's destinations. The response includes the destination that served the request and the reason that the router chose it.
The following limits apply:
-
The maximum request payload is 6 MB. A request with a larger body fails with HTTP status code 413.
-
Your model has up to 60 seconds for each attempt, the same limit as
InvokeEndpoint. If your account has a higher model execution timeout forInvokeEndpoint, it doesn't apply through an inference router. For models that take longer, useInvokeInferenceRouterAsync.
If a destination returns an error that the router can retry, such as a throttling error, before your model produces a response, the router retries the request once on another destination. A request that times out on a destination isn't retried. Because a request can make two attempts, set your client read timeout to at least 170 seconds.
The caller needs permission to invoke the inference router and every destination of the routing target. For information about permissions, see Route requests across Regions with inference routers.
Parameter Syntax
$result = $client->invokeInferenceRouter([
'Accept' => '<string>',
'Body' => <string || resource || Psr\Http\Message\StreamInterface>, // REQUIRED
'ContentType' => '<string>',
'CustomAttributes' => '<string>',
'InferenceId' => '<string>',
'InferenceRouterName' => '<string>', // REQUIRED
'PrefixAwareId' => '<string>',
'RoutingTargetName' => '<string>', // REQUIRED
]);
Parameter Details
Members
- Accept
-
- Type: string
The MIME type that you want for the inference response. The router passes it to the destination.
- Body
-
- Required: Yes
- Type: blob (string|resource|Psr\Http\Message\StreamInterface)
The input data for the inference, in the format that your model expects. The body can't be empty.
- ContentType
-
- Type: string
The MIME type of the input data in the request body. The router passes it to the destination.
- CustomAttributes
-
- Type: string
Provides additional information about the inference request. The value is an opaque string that the router passes, unchanged, to the model container of the destination that serves the request. The value can contain up to 1,024 visible US-ASCII characters.
- InferenceId
-
- Type: string
An identifier for the inference request. The router passes it to the destination.
- InferenceRouterName
-
- Required: Yes
- Type: string
The name of the inference router to invoke.
- PrefixAwareId
-
- Type: string
An optional, stable identifier that serves as a routing hint for prefix-aware routing. The router passes it to the destination that serves the request. Within that destination, requests with the same prefix and the same identifier go to the same instance. If requests from different applications might have the same prompt prefix, set a different identifier for each application to differentiate their routing decisions.
Applies only to destination endpoints configured with a
RoutingStrategyofPREFIX_AWARE. - RoutingTargetName
-
- Required: Yes
- Type: string
The name of the routing target in the inference router. The routing target lists the destinations that can serve the request.
Result Syntax
[
'Body' => <string || resource || Psr\Http\Message\StreamInterface>,
'ContentType' => '<string>',
'CustomAttributes' => '<string>',
'InvokedProductionVariant' => '<string>',
'InvokedRoutedResourceArn' => '<string>',
'RoutingReason' => '<string>',
]
Result Details
Members
- Body
-
- Type: blob (string|resource|Psr\Http\Message\StreamInterface)
The inference that the model returned.
- ContentType
-
- Type: string
The MIME type of the inference returned in the response body.
- CustomAttributes
-
- Type: string
Provides additional information in the response about the inference. This is the value that the model container of the destination returned, unchanged.
- InvokedProductionVariant
-
- Type: string
The production variant of the destination endpoint that served the request.
- InvokedRoutedResourceArn
-
- Type: string
The Amazon Resource Name (ARN) of the endpoint or inference component that served the request.
- RoutingReason
-
- Type: string
The reason that the router chose the destination that served the request. Possible values:
-
local-preferred– The destination is a healthy destination in the router's Region. -
capacity-available– No destination in the router's Region could take the request, and two or more destinations in other Regions could. -
only-healthy– No destination in the router's Region could take the request, and exactly one destination in another Region could. -
failover– The router moved the request away from destinations in its Region because they were overloaded or returning errors. You also see this value when the router can't assess destination health, and when no destination is healthy and the router tries one anyway.
Errors
- ValidationException:
The request isn't valid. Check the inference router name, the routing target name, and the request parameters, and then try again.
- AccessDeniedException:
You don't have permission to perform this action. Check that the caller is allowed to invoke the inference router and every destination of the routing target.
- ServiceUnavailableException:
The service is temporarily unavailable. For example, no destination of the routing target could serve the request, or a destination didn't respond. Retry the request with exponential backoff. The Amazon Web Services SDKs and the Amazon Web Services CLI do this by default.
- ModelError:
The model in the destination that served the request returned an error. Check
OriginalStatusCode,OriginalMessage, and the destination's logs in Amazon CloudWatch.- ThrottlingException:
The request was denied because you exceeded the request rate for the inference router, or because a destination throttled the request. Retry the request with exponential backoff.
- RequestTimeoutException:
The inference router didn't receive the complete request within 300 seconds of accepting it, for example because of a very slow upload. Retry the request.
- InternalDependencyException:
The request failed because of an error in an internal dependency. Retry the request with exponential backoff.
- InternalFailure:
An internal error occurred. Retry the request with exponential backoff. The Amazon Web Services SDKs and the Amazon Web Services CLI do this by default.
- ModelNotReadyException:
The destination isn't ready to serve the model, for example because an inference component has no copies. Retry the request later.
Examples
Example 1: Invoke an inference router
The following example sends a JSON request to the my-target routing target of the my-router inference router. The response shows that a destination in the router's Region served the request.
$result = $client->invokeInferenceRouter([
'Body' => <BLOB>,
'ContentType' => 'application/json',
'InferenceRouterName' => 'my-router',
'RoutingTargetName' => 'my-target',
]);
Result syntax:
[
'ContentType' => 'application/json',
'RoutingReason' => 'local-preferred',
]
InvokeInferenceRouterAsync
$result = $client->invokeInferenceRouterAsync([/* ... */]); $promise = $client->invokeInferenceRouterAsyncAsync([/* ... */]);
Submits an asynchronous inference request to an inference router. Before you call this operation, upload the input data to Amazon S3 in the router's Amazon Web Services Region. The router returns as soon as it accepts the request, and sends the request to one of the destinations of the routing target. The destination reads the input from Amazon S3, and the inference response is written to the Amazon S3 output path that the routing target specifies.
If a destination doesn't start the request within the routing target's MaxTimeInBacklogSeconds, the router moves the request to another destination. After your model starts processing the request, the request doesn't move. If no destination can take the request before RequestTTLSeconds runs out, or every destination has been tried, the router writes a failure object to the FailureLocation and publishes a notification to the routing target's error topic, if one is configured.
For information about the permissions that the caller and each destination need, see Send asynchronous requests through an inference router.
Parameter Syntax
$result = $client->invokeInferenceRouterAsync([
'Accept' => '<string>',
'ContentType' => '<string>',
'CustomAttributes' => '<string>',
'Filename' => '<string>',
'InferenceId' => '<string>',
'InferenceRouterName' => '<string>', // REQUIRED
'InputLocation' => '<string>', // REQUIRED
'InvocationTimeoutSeconds' => <integer>,
'RequestTTLSeconds' => <integer>,
'RoutingTargetName' => '<string>', // REQUIRED
'S3OutputPathExtension' => '<string>',
]);
Parameter Details
Members
- Accept
-
- Type: string
The MIME type that you want for the inference response. The router passes it to the destination.
- ContentType
-
- Type: string
The MIME type of the input data in Amazon S3. The router passes it to the destination.
- CustomAttributes
-
- Type: string
Provides additional information about the inference request. The value is an opaque string that the router passes, unchanged, to the model container of the destination that serves the request. The value can contain up to 1,024 visible US-ASCII characters.
- Filename
-
- Type: string
The file name of the inference response stored in Amazon S3. If you don't provide one, SageMaker AI generates one.
- InferenceId
-
- Type: string
An identifier for the inference request. If you don't provide one, SageMaker AI generates one and returns it in the response.
- InferenceRouterName
-
- Required: Yes
- Type: string
The name of the inference router to invoke.
- InputLocation
-
- Required: Yes
- Type: string
The Amazon S3 URI of the object that contains the input data for the inference. The bucket must be in the inference router's Amazon Web Services Region and owned by the router's account. The destination endpoint's execution role reads the object, and the destination's asynchronous inference limits apply to it.
- InvocationTimeoutSeconds
-
- Type: int
The maximum time, in seconds, that a destination can spend processing the request before the request is marked as expired. The default is 900 seconds (15 minutes).
- RequestTTLSeconds
-
- Type: int
The time to live of the request, in seconds, measured from when the router accepts it. If no destination starts the request in this time, the request fails. The default is 21,600 seconds (6 hours).
- RoutingTargetName
-
- Required: Yes
- Type: string
The name of the routing target in the inference router. The routing target must be configured for asynchronous inference.
- S3OutputPathExtension
-
- Type: string
The path extension that is appended to the routing target's Amazon S3 output path where the inference response is stored.
Result Syntax
[
'FailureLocation' => '<string>',
'InferenceId' => '<string>',
'OutputLocation' => '<string>',
]
Result Details
Members
- FailureLocation
-
- Type: string
The Amazon S3 URI where the failure details are written if the inference fails.
- InferenceId
-
- Type: string
The identifier for the inference request. This is the
InferenceIdthat you provided, or the one that SageMaker AI generated. - OutputLocation
-
- Type: string
The Amazon S3 URI where the inference response is written. The location doesn't change if the router moves the request to another destination.
Errors
- ValidationException:
The request isn't valid. Check the inference router name, the routing target name, and the request parameters, and then try again.
- AccessDeniedException:
You don't have permission to perform this action. Check that the caller is allowed to invoke the inference router and every destination of the routing target.
- ServiceUnavailableException:
The service is temporarily unavailable. For example, no destination of the routing target could serve the request, or a destination didn't respond. Retry the request with exponential backoff. The Amazon Web Services SDKs and the Amazon Web Services CLI do this by default.
- ThrottlingException:
The request was denied because you exceeded the request rate for the inference router, or because a destination throttled the request. Retry the request with exponential backoff.
- RequestTimeoutException:
The inference router didn't receive the complete request within 300 seconds of accepting it, for example because of a very slow upload. Retry the request.
- InternalFailure:
An internal error occurred. Retry the request with exponential backoff. The Amazon Web Services SDKs and the Amazon Web Services CLI do this by default.
Shapes
AccessDeniedException
Description
You don't have permission to perform this action. Check that the caller is allowed to invoke the inference router and every destination of the routing target.
Members
- Message
-
- Type: string
A message that describes the error.
InternalDependencyException
Description
The request failed because of an error in an internal dependency. Retry the request with exponential backoff.
Members
- Message
-
- Type: string
A message that describes the error.
InternalFailure
Description
An internal error occurred. Retry the request with exponential backoff. The Amazon Web Services SDKs and the Amazon Web Services CLI do this by default.
Members
- Message
-
- Type: string
A message that describes the error.
ModelError
Description
The model in the destination that served the request returned an error. Check OriginalStatusCode, OriginalMessage, and the destination's logs in Amazon CloudWatch.
Members
- LogStreamArn
-
- Type: string
The Amazon Resource Name (ARN) of the Amazon CloudWatch log stream for the destination that served the request.
- Message
-
- Type: string
A message that describes the error.
- OriginalMessage
-
- Type: string
The error message that the model container returned.
- OriginalStatusCode
-
- Type: int
The HTTP status code that the model container returned.
ModelNotReadyException
Description
The destination isn't ready to serve the model, for example because an inference component has no copies. Retry the request later.
Members
- Message
-
- Type: string
A message that describes the error.
RequestTimeoutException
Description
The inference router didn't receive the complete request within 300 seconds of accepting it, for example because of a very slow upload. Retry the request.
Members
- Message
-
- Type: string
A message that describes the error.
ServiceUnavailableException
Description
The service is temporarily unavailable. For example, no destination of the routing target could serve the request, or a destination didn't respond. Retry the request with exponential backoff. The Amazon Web Services SDKs and the Amazon Web Services CLI do this by default.
Members
- Message
-
- Type: string
A message that describes the error.
ThrottlingException
Description
The request was denied because you exceeded the request rate for the inference router, or because a destination throttled the request. Retry the request with exponential backoff.
Members
- Message
-
- Type: string
A message that describes the error.
ValidationException
Description
The request isn't valid. Check the inference router name, the routing target name, and the request parameters, and then try again.
Members
- Message
-
- Type: string
A message that describes the error.